INDEX

Explanations

positive adjectives describing something of significant importance or impact

oai_token-act-pair · gpt-3.5-turbo

adjectives conveying a sense of significance or impact

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ults

-0.96

ses

-0.86

ravings

-0.85

doms

-0.82

assies

-0.82

bots

-0.80

apses

-0.79

apons

-0.79

 Surve

-0.79

units

-0.77

POSITIVE LOGITS

 understatement

0.98

 sleeper

0.88

 antidote

0.87

 reminder

0.82

 boon

0.81

 example

0.79

 contender

0.79

 spoiler

0.76

 fundraiser

0.76

 spokesperson

0.76

Activations Density 0.580%

positive adjectives describing something of significant importance or impact

adjectives conveying a sense of significance or impact

No Comments

No Known Activations